Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add espennilsen/pi --skill pi-memorygit clone --depth 1 https://github.com/espennilsen/piWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/espennilsen/pi/pi-memory)<a href="https://agentmods.dev/skills/espennilsen/pi/pi-memory"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/pi-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/espennilsen/pi/pi-memory"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/pi-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00898 |
| Opus 5.5 | $0.00018 | $0.00359 |
| Sonnet 5.5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
pi-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-memory — Persistent Memory
A file-based memory system that persists knowledge across sessions using plain Markdown.
Architecture
<base-path>/
├── MEMORY.md # Long-term curated memory (facts, preferences, decisions)
└── memory/
├── 2026-02-11.md # Daily log — append-only session notes
├── 2026-02-10.md
└── ...
- MEMORY.md — The "brain". Organized into
## Sections. Survives compaction. Editable in place. - memory/YYYY-MM-DD.md — Daily append-only logs. Timestamped entries. One file per day.
The base path defaults to cwd. Override with settings.json:
{ "pi-memory": { "path": "/path/to/memory/dir" } }
Tools
memory_read
Read memory contents.
| target | description |
|---|---|
long_term |
Read full MEMORY.md |
daily |
Read a specific date's log (default: today). Pass date: "YYYY-MM-DD" for other dates. |
list |
List all available daily log files |
memory_write
Write to memory.
| target | description |
|---|---|
daily |
Append a timestamped entry to today's log. Used for session notes, progress, decisions. |
long_term |
Update MEMORY.md. Pass section to replace a specific ## Section, or omit to append. |
Long-term memory sections — use section parameter to target:
memory_write target=long_term section="Preferences" content="- Prefers dark theme\n- Terminal-first tools"
This replaces the content under ## Preferences. If the section doesn't exist, it's created.
Daily log entries — auto-timestamped:
memory_write target=daily content="Completed the auth refactor. Using JWT with RS256."
Creates ### HH:MM entry in today's file.
memory_search
Full-text search across MEMORY.md and all daily logs.
memory_search query="JWT" limit=10
Returns matching lines with ±1 line of context, grouped by file.
When to Write Memory
Always write to long-term memory when:
- User explicitly says "remember this", "save this", "note that..."
- You learn a new preference, convention, or decision
- A significant architectural or design choice is made
- You discover something about the user's workflow or environment
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 129 lines · 44 tokens per session scan A 23db2c1f7720
pi-memory is a skill published in the GitHub repository espennilsen/pi (122 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 898 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.